论文部分内容阅读
股票价格买卖差是衡量金融市场流动性和有效性的重要指标,已经得到学术界的广泛研究。相比而言,作为衡量股票市场风险的重要因素的股票价格买卖价差的波动率却没有得到相同的重视。在广义自回归条件异方差(generalized autoregressive conditional heteroscedasticity,GARCH)模型的基础上,提出了GARCH-neural network(GARCH-NN)混合模型分析股票价格买卖价差波动率的动态性。以深圳证券交易所成分股价指数的高频数据为样本对所提模型进行了实证分析。运用GARCH家族模型对股票价格买卖差波动率的动态性进行分析,得出预测效果最优的GARCH模型。在最优GARCH模型的基础上结合神经网络分析方法即GARCH-NN混合模型对样本数据进行了实证分析。比较分析最优GARCH模型和GARCH-NN混合模型对股票价格买卖差波动率的预测效果,并以AIC(Akaike information criterion)和BIC(Bayesian information criterion)作为检验模型预测效果的指标。实证结果表明,提出的GARCH-NN混合模型更优。
The spread of the stock price is an important index to measure the liquidity and effectiveness of financial markets. It has been widely studied in academia. In contrast, the volatility of the bid-ask spread, an important measure of stock market risk, has not received the same attention. Based on the generalized autoregressive conditional heteroscedasticity (GARCH) model, a GARCH-neural network (GARCH-NN) hybrid model is proposed to analyze the dynamics of volatility of stock price bid-ask spread. Taking the high frequency data of the constituent stock price index of Shenzhen Stock Exchange as samples, the model is empirically analyzed. Using the GARCH family model to analyze the dynamics of volatility of stock price volatility, the GARCH model with the best forecasting effect is obtained. Based on the optimal GARCH model and the neural network analysis method, namely the GARCH-NN mixed model, the sample data are empirically analyzed. The effect of the optimal GARCH model and the GARCH-NN mixed model on the volatility of the stock price trading volatility is compared and analyzed. The AIC (Akaike information criterion) and BIC (Bayesian information criterion) are used as the indicators to predict the effect of the model. The empirical results show that the proposed GARCH-NN hybrid model is better.